Extracting data from executive employment agreements
Companies sign an employment agreement with each senior executive, its terms negotiated clause by clause by counsel on both sides. Public companies file them as SEC exhibits, and a buyer reviews one for every executive at the target during diligence. Most arrive as executed PDFs or signed scans in a data room.
Diligence needs the term dates, base salary, target bonus, severance multiple and change-of-control trigger. A deal model totals the payments a sale would trigger and tests them against the golden parachute rules of Section 280G.
What makes executive employment agreements hard
The terms are clauses
Salary and notice terms sit inside numbered clauses of running prose, often with two terms sharing one sentence.
Payouts depend on how employment ends
Severance turns on why employment ends: termination without cause, resignation for good reason or a change of control can each pay a different multiple.
The copy that counts is signed
In a data room, the copy that counts is the executed one: often a scan with handwritten dates and wet-ink signatures.
Parse, extract, verify
Parse
Parse turns the document into reading-order Markdown and a hierarchy of blocks (text, tables, figures), and grounds each block to its exact location on the page.
Extract
You define the fields in a JSON schema, and Extract returns their values in a consistent, structured format, each linked back to where it appears in the Markdown.
Verify
Each value links back to where it appears, down to the character range in the Markdown, and the page and bounding box in the source document, so every result can be verified.
One executive employment agreement, end to end
About this document: An executed employment agreement between the Bethlehem Central School District in New York and its Superintendent of Schools, posted by the district as a public record. Thirteen portrait pages, scanned from the wet-ink original: recitals and 18 numbered sections, then signatures and two notary acknowledgments. Page 2 carries the term and compensation.
Processing objective: The objective is to capture the commercial core of the agreement: how long it runs and what it pays each year. Salary and the raise are each written in words and then in figures, and each value grounds to the line carrying the figure.
Demonstration fields: Term start, Term end, Base salary, Annual increase, Longevity payment
The document
4 of 13 pages
Page 1
Page 2shown below
Page 5
Page 8
Where each value came from
term.start_date
{
"value": "July 1, 2025",
"page": 2,
"range": {
"end": 2742,
"start": 2659
},
"box": {
"xmin": 0.1855,
"ymin": 0.21033,
"xmax": 0.89516,
"ymax": 0.22788
}
}term.end_date
{
"value": "June 30, 2030",
"page": 2,
"range": {
"end": 2742,
"start": 2659
},
"box": {
"xmin": 0.1855,
"ymin": 0.21033,
"xmax": 0.89516,
"ymax": 0.22788
}
}compensation.base_salary
{
"value": 235553,
"page": 2,
"range": {
"end": 3181,
"start": 3104
},
"box": {
"xmin": 0.24265,
"ymin": 0.36209,
"xmax": 0.89532,
"ymax": 0.38013
}
}compensation.annual_increase_percent
{
"value": 4,
"page": 2,
"range": {
"end": 3258,
"start": 3182
},
"box": {
"xmin": 0.24256,
"ymin": 0.38017,
"xmax": 0.89501,
"ymax": 0.39755
}
}compensation.longevity_payments[2].amount
{
"value": 7500,
"page": 2,
"range": {
"end": 4244,
"start": 4163
},
"box": {
"xmin": 0.24107,
"ymin": 0.62136,
"xmax": 0.89505,
"ymax": 0.63904
}
}How to try it yourself
Everything on this page is reproducible. The sample, its schema, and the Parse and Extract API outputs are published. You can repeat the same two calls from whichever surface you already build on.
- Claude Skilldescribe the job; the agent writes it
- CLIno code at all
- MCPexpose ADE docs as an agent tool
- REST APIany language
- Pythonlandingai-ade
- TypeScriptlandingai-ade
Documents into data
Accurate
The best accuracy on the difficult documents other tools get wrong, such as messy scans, complicated tables, checkboxes and handwriting.
Auditable
Every answer cites its sources. Values come back with an audit trail (page, bounding box, character range) so a human can review them.
Agentic
Applies multi-step reasoning, and plans before it acts. Handles documents it has never seen before and adapts to variations.
API-first
Composable APIs that drop into any tech stack and can be called from anywhere. Easy to build on and embed in your pipelines and products.
Affordable
Cost-competitive rates with complete price transparency. Spend controls before you run, and every job reports its exact cost.
Enterprise-grade
Built for production and scale from day one. Fully observable and monitored, running securely in our cloud or yours.
Built for high-volume, high-throughput production
- Zero data retention
- Priority rate limits
- Enhanced support
- VPC and on-prem deployment
Available on Team and Enterprise plans. VPC and on-prem deployment require an Enterprise plan.
